5 papers · 1 filter
HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding
Leon Mayer, Lucas Luttner, Patrick Godau +42
Recent advances in Vision-Language Models (VLMs) have led to rapid progress in video understanding across a wide range of benchmark tasks. However, existing evaluations largely foc…
Limitations of Synthetic Data Generation in Specialized Data-Scarce Domains
Edward Zhang, Marcel Hussing, Tanay Tandon +12
Advances in diffusion-based generative models have motivated the use of synthetic image generation to alleviate data scarcity in vision tasks. While this strategy has shown promise…
Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs
Guiqiu Liao, Matjaz Jogan, Daniel A. Hashimoto
Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and lim…
Active Learning for Efficient Annotation of Surgical Videos with Weak Supervision
Manasa Dendukuri, Matjaz Jogan, Daniel A. Hashimoto +1
Precise spatial-temporal annotation of laparoscopic videos is time-consuming and requires expert knowledge. We propose a human-in-the-loop knowledge acquisition framework that comb…
DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction
Guiqiu Liao, Matjaž Jogan, Daniel A. Hashimoto
Dense prediction tasks in surgical computer vision, such as segmentation and surgical zone prediction, can provide valuable guidance for laparoscopic and robotic surgery. However,…